Integrating geostatistical methods and deep learning for enhanced 87Sr/86Sr isoscape Estimation: A case study in South Korea

The 87Sr/86Sr isotopic ratio has emerged as a valuable geochemical tracer in fields such as environmental forensics, archaeology, and provenance research. However, generating accurate and spatially continuous isoscape maps from sparse isotopic measurements remains a major challenge due to limited da...

Full description

Saved in:
Bibliographic Details
Main Authors: Hyeongmok Lee, Go-Eun Kim, Woo-Jin Shin, Yuyoung Lee, Sanghee Park, Kwang-Sik Lee, Jina Jeong, Seung-Ik Park, Sungwook Choung
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:International Journal of Applied Earth Observations and Geoinformation
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1569843225003449
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849240739933847552
author Hyeongmok Lee
Go-Eun Kim
Woo-Jin Shin
Yuyoung Lee
Sanghee Park
Kwang-Sik Lee
Jina Jeong
Seung-Ik Park
Sungwook Choung
author_facet Hyeongmok Lee
Go-Eun Kim
Woo-Jin Shin
Yuyoung Lee
Sanghee Park
Kwang-Sik Lee
Jina Jeong
Seung-Ik Park
Sungwook Choung
author_sort Hyeongmok Lee
collection DOAJ
description The 87Sr/86Sr isotopic ratio has emerged as a valuable geochemical tracer in fields such as environmental forensics, archaeology, and provenance research. However, generating accurate and spatially continuous isoscape maps from sparse isotopic measurements remains a major challenge due to limited data availability and spatial heterogeneity. To address this, we propose a hybrid framework for 87Sr/86Sr isoscape mapping that integrates a kriging-based data augmentation method with a deep learning (DL) classifier. The kriging component generates synthetic training samples by interpolating sparse isotopic data while preserving underlying spatial correlations and geological anisotropy. These augmented data, along with spatial geological features (e.g., lithology, tectonic settings) and geochemical compositions, are used as input variables for training a feedforward deep neural network. The approach was applied to 409 soil samples collected across South Korea, and its performance was benchmarked against conventional kriging and convolutional neural networks (CNN). The proposed model achieved significantly higher classification accuracy (91.67%) compared to kriging-based and CNN-based models (76.7% and 86.7%, respectively). Furthermore, the isoscape outputs revealed meaningful isotopic patterns linked to geological and geomorphological controls, such as metamorphic rock distributions, fault density, and surface slope. This framework demonstrates the effectiveness of combining geostatistics with DL to improve predictive accuracy and interpretability in isotopic provenance research and environmental monitoring.
format Article
id doaj-art-8a5aae0338ad4e579897970181cb3acf
institution Kabale University
issn 1569-8432
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series International Journal of Applied Earth Observations and Geoinformation
spelling doaj-art-8a5aae0338ad4e579897970181cb3acf2025-08-20T04:00:27ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322025-08-0114210469710.1016/j.jag.2025.104697Integrating geostatistical methods and deep learning for enhanced 87Sr/86Sr isoscape Estimation: A case study in South KoreaHyeongmok Lee0Go-Eun Kim1Woo-Jin Shin2Yuyoung Lee3Sanghee Park4Kwang-Sik Lee5Jina Jeong6Seung-Ik Park7Sungwook Choung8Department of Geology, Kyungpook National University, Daegu 41566, Republic of KoreaGraduate School of Analytical Science and Technology, Chungnam National University, Daejeon 34134, Republic of Korea; Geoanalysis Center, Korea Institute of Geoscience and Mineral Resources, Daejeon 34132, Republic of KoreaResearch Center of Earth and Environmental Sciences, Korea Basic Science Institute, Cheongju 28119, Republic of KoreaResearch Center of Earth and Environmental Sciences, Korea Basic Science Institute, Cheongju 28119, Republic of KoreaResearch Center of Earth and Environmental Sciences, Korea Basic Science Institute, Cheongju 28119, Republic of KoreaGraduate School of Analytical Science and Technology, Chungnam National University, Daejeon 34134, Republic of Korea; Research Center of Earth and Environmental Sciences, Korea Basic Science Institute, Cheongju 28119, Republic of KoreaDepartment of Geology, Kyungpook National University, Daegu 41566, Republic of Korea; Corresponding author.Department of Geology, Kyungpook National University, Daegu 41566, Republic of KoreaResearch Center of Earth and Environmental Sciences, Korea Basic Science Institute, Cheongju 28119, Republic of Korea; Department of Environmental System Engineering, Korea University, Sejong 30019, Republic of KoreaThe 87Sr/86Sr isotopic ratio has emerged as a valuable geochemical tracer in fields such as environmental forensics, archaeology, and provenance research. However, generating accurate and spatially continuous isoscape maps from sparse isotopic measurements remains a major challenge due to limited data availability and spatial heterogeneity. To address this, we propose a hybrid framework for 87Sr/86Sr isoscape mapping that integrates a kriging-based data augmentation method with a deep learning (DL) classifier. The kriging component generates synthetic training samples by interpolating sparse isotopic data while preserving underlying spatial correlations and geological anisotropy. These augmented data, along with spatial geological features (e.g., lithology, tectonic settings) and geochemical compositions, are used as input variables for training a feedforward deep neural network. The approach was applied to 409 soil samples collected across South Korea, and its performance was benchmarked against conventional kriging and convolutional neural networks (CNN). The proposed model achieved significantly higher classification accuracy (91.67%) compared to kriging-based and CNN-based models (76.7% and 86.7%, respectively). Furthermore, the isoscape outputs revealed meaningful isotopic patterns linked to geological and geomorphological controls, such as metamorphic rock distributions, fault density, and surface slope. This framework demonstrates the effectiveness of combining geostatistics with DL to improve predictive accuracy and interpretability in isotopic provenance research and environmental monitoring.http://www.sciencedirect.com/science/article/pii/S1569843225003449Strontium isotope ratioSecondary informationDeep learningGeostatistical data augmentation methodUncertainty estimation
spellingShingle Hyeongmok Lee
Go-Eun Kim
Woo-Jin Shin
Yuyoung Lee
Sanghee Park
Kwang-Sik Lee
Jina Jeong
Seung-Ik Park
Sungwook Choung
Integrating geostatistical methods and deep learning for enhanced 87Sr/86Sr isoscape Estimation: A case study in South Korea
International Journal of Applied Earth Observations and Geoinformation
Strontium isotope ratio
Secondary information
Deep learning
Geostatistical data augmentation method
Uncertainty estimation
title Integrating geostatistical methods and deep learning for enhanced 87Sr/86Sr isoscape Estimation: A case study in South Korea
title_full Integrating geostatistical methods and deep learning for enhanced 87Sr/86Sr isoscape Estimation: A case study in South Korea
title_fullStr Integrating geostatistical methods and deep learning for enhanced 87Sr/86Sr isoscape Estimation: A case study in South Korea
title_full_unstemmed Integrating geostatistical methods and deep learning for enhanced 87Sr/86Sr isoscape Estimation: A case study in South Korea
title_short Integrating geostatistical methods and deep learning for enhanced 87Sr/86Sr isoscape Estimation: A case study in South Korea
title_sort integrating geostatistical methods and deep learning for enhanced 87sr 86sr isoscape estimation a case study in south korea
topic Strontium isotope ratio
Secondary information
Deep learning
Geostatistical data augmentation method
Uncertainty estimation
url http://www.sciencedirect.com/science/article/pii/S1569843225003449
work_keys_str_mv AT hyeongmoklee integratinggeostatisticalmethodsanddeeplearningforenhanced87sr86srisoscapeestimationacasestudyinsouthkorea
AT goeunkim integratinggeostatisticalmethodsanddeeplearningforenhanced87sr86srisoscapeestimationacasestudyinsouthkorea
AT woojinshin integratinggeostatisticalmethodsanddeeplearningforenhanced87sr86srisoscapeestimationacasestudyinsouthkorea
AT yuyounglee integratinggeostatisticalmethodsanddeeplearningforenhanced87sr86srisoscapeestimationacasestudyinsouthkorea
AT sangheepark integratinggeostatisticalmethodsanddeeplearningforenhanced87sr86srisoscapeestimationacasestudyinsouthkorea
AT kwangsiklee integratinggeostatisticalmethodsanddeeplearningforenhanced87sr86srisoscapeestimationacasestudyinsouthkorea
AT jinajeong integratinggeostatisticalmethodsanddeeplearningforenhanced87sr86srisoscapeestimationacasestudyinsouthkorea
AT seungikpark integratinggeostatisticalmethodsanddeeplearningforenhanced87sr86srisoscapeestimationacasestudyinsouthkorea
AT sungwookchoung integratinggeostatisticalmethodsanddeeplearningforenhanced87sr86srisoscapeestimationacasestudyinsouthkorea